The migration period for updating V1 Machine Learning Service instances (created prior to September 1, 2020) to V2 Machine Learning service instances will end on April 8, 2021. End of support for deprecated V3 and V4-beta Watson Machine Learning APIs is also April 8, 2021. If you have not yet migrated your V1 assets to a V2 service instance, you will get errors when trying to run deployments. The migration process is as follows:
Create a deployment space where you will migrate your assets. Note: this does not require Watson Studio.
Migrate your assets, using either the Watson Studio migration tool or the Watson Machine Learning V4 APIs.
Provision a V2 machine learning service instance and associate it with the space. Note: you will also need to associate a V2 service instance with your project to work with AutoAI or Deep Learning experiments.
Deploy models to the deployment space. In some cases, you will need to make code changes to use new APIS and frameworks.
Delete V1 service instances.
Remove V3 APIs and extend coverage of V4 APIs
https://cloud.ibm.com/apidocs/machine-learning